Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms of service and licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gender
    0.45
    venues
    0.45
     ਨਹੀਂ
    0.45
    portional
    0.45
    roversial
    0.45
    ount
    0.44
    oun
    0.43
    onymous
    0.43
    ack
    0.42
    subscription
    0.42
    POSITIVE LOGITS
     Trabajo
    0.49
    学习
    0.48
     파일을
    0.48
     hereafter
    0.47
     处理
    0.46
     Máy
    0.45
     Thiết
    0.45
    发现
    0.44
     учеб
    0.44
    的学习
    0.43
    Act Density 0.003%

    No Known Activations